Project_EDA_Working.Rmd

---
title: "Project_EDA_Working"
author: "Maria Martinez"
date: "2024-11-01"
output: html_document
---

```{r setup, include=FALSE}
knitr::opts_chunk$set(echo = TRUE)
```

## R Markdown

This is an R Markdown document. Markdown is a simple formatting syntax for authoring HTML, PDF, and MS Word documents. For more details on using R Markdown see <http://rmarkdown.rstudio.com>.

When you click the **Knit** button a document will be generated that includes both content as well as the output of any embedded R code chunks within the document. You can embed an R code chunk like this:

```{r cars}
summary(cars)
```

## Including Plots

You can also embed plots, for example:

```{r pressure, echo=FALSE}
plot(pressure)
```

Note that the `echo = FALSE` parameter was added to the code chunk to prevent printing of the R code that generated the plot.
```{r}
```


```{r}
library(dplyr)
library(tidyr)
library(ggplot2)
library(ggcorrplot)
library(MASS)

```


```{r}
rm(list = ls())
getwd()
```


```{r}
data1 <- read.csv("health_struct.csv", header = TRUE)
str(data1)
```
```{r}
#Convert categorical variables (Nominal variables)
data1$Gender <- as.factor(data1$Gender)
data1$SmokingStatus <- as.factor(data1$SmokingStatus)
data1$AlcoholConsumption <- as.factor(data1$AlcoholConsumption)
data1$ExerciseFrequency <- as.factor(data1$ExerciseFrequency)
data1$Diabetes <- as.factor(data1$Diabetes)
data1$HeartDisease <- as.factor(data1$HeartDisease)
data1$PhysicalActivityLevel <- as.factor(data1$PhysicalActivityLevel)
data1$DietQuality <- as.factor(data1$DietQuality)
data1$MedicationAdherence <- as.factor(data1$MedicationAdherence)

```


```{r}
#Specify order of levels for Ordinal Variables
data1$Outcome <- factor(data1$Outcome, levels = c("Healthy", "At Risk", "Critical"))
data1$Systolic <- factor(data1$Systolic, levels = c("Normal", "Elevated", "Hypertension_sg1", "Hypertension_sg2"))
data1$Diastolic <- factor(data1$Diastolic, levels = c("Normal", "Hypertension_sg1", "Hypertension_sg2"))
data1$LevelCho <- factor(data1$LevelCho, levels = c("Healthy", "At-risk", "High"))
data1$LevelBmi <- factor(data1$LevelBmi, levels = c("Underweight", "Normal weight", "Overweight", "Obese"))

data1$AlcoholConsumption <- factor(data1$AlcoholConsumption, levels = c("Never", "Occasionally", "Regularly"))
data1$ExerciseFrequency <- factor(data1$ExerciseFrequency, levels = c("Never", "Rarely", "Sometimes", "Often"))
data1$PhysicalActivityLevel <- factor(data1$PhysicalActivityLevel, levels = c("Low", "Medium", "High"))
data1$DietQuality <- factor(data1$DietQuality, levels = c("Poor", "Average", "Good"))
data1$MedicationAdherence <- factor(data1$MedicationAdherence, levels = c("Low", "Medium", "High"))


#Verify changes
str(data1)
colSums(is.na(data1))
any(is.na(data1))


```


```{r}
#View the Distribution of the target variable
table(data1$Outcome)/nrow(data1) * 100  # % of each class
Outcome_dist <- prop.table(table(data1$Outcome)) * 100
Outcome_dist
```


```{r}
ggplot(data1, aes(x = Outcome)) +
  geom_bar(fill = "skyblue") +
  geom_text(stat = 'count', aes(label = scales::percent(..count../sum(..count..))), vjust = -0.5) +
  labs(title = "Distribution of Outcome", x = "outcome", y = "count")


```

# Dataframes 

```{r}
Healthy_df <- filter(data1, Outcome == "Healthy")
AtRisk_df <- filter(data1, Outcome == "At Risk")
Critical_df <- filter(data1, Outcome == "Critical")

```

## Data structure in illness variables

### Diabetes
### Heart Disease
```{r}
data1 %>% group_by(Outcome, Diabetes)  %>% summarise(n= n())
data1 %>%  group_by(Outcome) %>% summarize(mean(Diabetes != "No"))
data1 %>%  group_by(Outcome) %>% summarize(mean(Diabetes != "Yes"))
data1 %>%  group_by(Outcome) %>% summarize(mean(HeartDisease != "No"))
data1 %>%  group_by(Outcome) %>% summarize(mean(HeartDisease != "Yes"))

```

### Level Cholesterol ***
```{r}
data1 %>%  group_by(Outcome) %>% summarize(mean(LevelCho == "Healthy"))
data1 %>%  group_by(Outcome) %>% summarize(mean(LevelCho == "At-risk"))
data1 %>%  group_by(Outcome) %>% summarize(mean(LevelCho == "High"))

```
### Level of BMI ***

```{r}
data1 %>%  group_by(Outcome) %>% summarize(mean(LevelBmi == "Underweight"))
data1 %>%  group_by(Outcome) %>% summarize(mean(LevelBmi == "Normal weight"))
data1 %>%  group_by(Outcome) %>% summarize(mean(LevelBmi == "Overweight"))
data1 %>%  group_by(Outcome) %>% summarize(mean(LevelBmi == "Obese"))
```

### Blood Pressure  (Systolic ***)

```{r}
data1 %>%  group_by(Outcome) %>% summarize(mean(Systolic == "Normal"))
data1 %>%  group_by(Outcome) %>% summarize(mean(Systolic == "Elevated"))
data1 %>%  group_by(Outcome) %>% summarize(mean(Systolic == "Hypertension_sg1"))
data1 %>%  group_by(Outcome) %>% summarize(mean(Systolic == "Hypertension_sg2"))

data1 %>%  group_by(Outcome) %>% summarize(mean(Diastolic == "Normal"))
data1 %>%  group_by(Outcome) %>% summarize(mean(Diastolic == "Hypertension_sg1"))
data1 %>%  group_by(Outcome) %>% summarize(mean(Diastolic == "Hypertension_sg2"))
```

## Data Structure on uncontrollable pre condition
### Genetic Risk - Distribution

```{r}
data1 %>% filter(GeneticRisk > 0) %>%
ggplot(aes(x=GeneticRisk, fill=Outcome)) + 
  geom_histogram(binwidth =0.1, alpha=0.1, position="identity") +
  xlim(0, 1) + 
  xlab("Genetic Risk") + ylab("Numbers of People") + 
  labs(title="Distribution of Genetic Risk by Outcome")

```

### Genetic Risk - Boxplot
```{r}

ggplot(data = data1, aes(x = Outcome, y = GeneticRisk)) +
  geom_boxplot(fill = "lightblue") +
  labs(title = "GeneticRisk vs Outcome", x = "Outcome", y = "Genetic Risk")

```
## Behaviors Variables Related to Health

### Smoking Status

```{r}
data1 %>%  group_by(Outcome) %>% summarize(mean(SmokingStatus == "Never"))
data1 %>%  group_by(Outcome) %>% summarize(mean(SmokingStatus == "Former"))
data1 %>%  group_by(Outcome) %>% summarize(mean(SmokingStatus == "Current"))


```

### Alcohol Consumption  *

```{r}

data1 %>%  group_by(Outcome) %>% summarize(mean(AlcoholConsumption == "Never"))
data1 %>%  group_by(Outcome) %>% summarize(mean(AlcoholConsumption == "Occasionally"))
data1 %>%  group_by(Outcome) %>% summarize(mean(AlcoholConsumption == "Regularly"))


```

### Exercise Frequency   **
```{r}
data1 %>%  group_by(Outcome) %>% summarize(mean(ExerciseFrequency == "Never"))
data1 %>%  group_by(Outcome) %>% summarize(mean(ExerciseFrequency == "Rarely"))
data1 %>%  group_by(Outcome) %>% summarize(mean(ExerciseFrequency == "Sometimes"))
data1 %>%  group_by(Outcome) %>% summarize(mean(ExerciseFrequency == "Often"))
```


### Physical Activity *
```{r}
data1 %>%  group_by(Outcome) %>% summarize(mean(PhysicalActivityLevel == "Low"))
data1 %>%  group_by(Outcome) %>% summarize(mean(PhysicalActivityLevel == "Medium"))
data1 %>%  group_by(Outcome) %>% summarize(mean(PhysicalActivityLevel == "High"))

```



### Diet Quality  **
```{r}
data1 %>%  group_by(Outcome) %>% summarize(mean(DietQuality == "Poor"))
data1 %>%  group_by(Outcome) %>% summarize(mean(DietQuality == "Average"))
data1 %>%  group_by(Outcome) %>% summarize(mean(DietQuality == "Good"))
```
## Demographics
### Gender


```{r}
### Gender
data1 %>%  group_by(Outcome) %>% summarize(mean(Gender == "Female"))
data1 %>%  group_by(Outcome) %>% summarize(mean(Gender == "Male"))
data1 %>%  group_by(Outcome) %>% summarize(mean(Gender == "Other"))

```

### Age
```{r}
data1 %>% filter(Age > 0) %>%
ggplot(aes(x=Age, fill=Outcome)) + 
  geom_histogram(binwidth =1, alpha=0.5, position="identity") +
  xlim(10, 100) + 
  xlab("Age") + ylab("Numbers of People") + 
  labs(title="Distribution of Age by Outcome")


```


##  Medication Adherence

```{r}
data1 %>%  group_by(Outcome) %>% summarize(mean(MedicationAdherence == "Low"))
data1 %>%  group_by(Outcome) %>% summarize(mean(MedicationAdherence == "Medium"))
data1 %>%  group_by(Outcome) %>% summarize(mean(MedicationAdherence == "High"))

```
## Annual Chechups


```{r}
data1 %>% filter(AnnualCheckups >= 0) %>%
ggplot(aes(x=AnnualCheckups, fill=Outcome)) + 
  geom_histogram(binwidth =1, alpha=0.5, position="identity") +
  xlim(0, 10) + 
  xlab("Annual Checups") + ylab("Numbers of People") + 
  labs(title="Distribution of Annual Checkups by Outcome")


```

## Healthcare Cost

```{r}

data1 %>% filter(HealthcareCost > 0) %>%
ggplot(aes(x=HealthcareCost, fill=Outcome)) + 
  geom_histogram(binwidth =1.0, alpha=1.0, position="identity") +
  xlim(0, 50000) + 
  xlab("Healthcare Cost") + ylab("Numbers of People") + 
  labs(title="Distribution of Healthcare Cost by Outcome")

data1 %>% filter(Outcome == "Healthy", HealthcareCost > 0) %>%
ggplot(aes(x=HealthcareCost, fill=Outcome)) + 
  geom_histogram(binwidth =1.0, alpha=1.0, position="identity") +
  xlim(0, 50000) + 
  xlab("Healthcare Cost") + ylab("Numbers of People") + 
  labs(title="Distribution of Healthcare Cost by Outcome")

data1 %>% filter(Outcome == "Critical", HealthcareCost > 0) %>%
ggplot(aes(x=HealthcareCost, fill=Outcome)) + 
  geom_histogram(binwidth =1.0, alpha=1.0, position="identity") +
  xlim(0, 50000) + 
  xlab("Healthcare Cost") + ylab("Numbers of People") + 
  labs(title="Distribution of Healthcare Cost by Outcome")


```


```{r}

ggplot(data = data1, aes(x = Outcome, y = HealthcareCost)) +
  geom_boxplot(fill = "lightblue") +
  labs(title = "Outcome vs Healthcare Cost", x = "Outcome", y = "Healthcare Cost")



```